tailscale-setup
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the connection of the agent to external Model Context Protocol (MCP) servers, creating a surface for processing untrusted data.
- Ingestion points: Data and tool responses from MCP servers integrated via Tailscale (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in server responses.
- Capability inventory: The agent's capabilities include network access to hosts and ports defined in the Tailscale policy file.
- Sanitization: No sanitization or validation procedures are provided for data retrieved from the tailnet hosts.
- [SAFE]: The skill consists of documentation for setting up a private network connection using Tailscale. It provides clear security recommendations, such as using tags and narrowing ACL policies to limit the agent's network reach to only necessary hosts.
Audit Metadata